uRP: An integrated research platform for one-stop analysis of medical images

Frontiers in Radiology, Journal Year: 2023, Volume and Issue: 3

Published: April 18, 2023

Medical image analysis is of tremendous importance in serving clinical diagnosis, treatment planning, as well prognosis assessment. However, the process usually involves multiple modality-specific software and relies on rigorous manual operations, which time-consuming potentially low reproducible.

Language: Английский

---

Regional and global hotspots of arsenic contamination of topsoil identified by deep learning

Communications Earth & Environment, Journal Year: 2024, Volume and Issue: 5(1)

Published: Jan. 3, 2024

Abstract Topsoil arsenic (As) contamination threatens the ecological environment and human health. However, traditional methods for As identification rely on on-site sampling chemical analysis, which are cumbersome, time-consuming, costly. Here we developed a method combining visible near infrared spectra deep learning to predict topsoil content. We showed that optimum fully connected neural network model had high robustness generalization (R-Square values of 0.688 0.692 validation testing sets). Using model, relative content at regional global scales were estimated populations might potentially be affected determined. found China, Brazil, California As-contamination hotspots. Other areas, e.g., Gabon, although also great risk, rarely documented, making them potential Our results provided guidance regions require more detailed detection or timely soil remediation can assist in alleviating topsoil-As contamination.

Language: Английский

---

SegRap2023: A benchmark of organs-at-risk and gross tumor volume Segmentation for Radiotherapy Planning of Nasopharyngeal Carcinoma

Medical Image Analysis, Journal Year: 2025, Volume and Issue: 101, P. 103447 - 103447

Published: Jan. 2, 2025

Language: Английский

---

Development and validation of fully automated robust deep learning models for multi-organ segmentation from whole-body CT images

Physica Medica, Journal Year: 2025, Volume and Issue: 130, P. 104911 - 104911

Published: Feb. 1, 2025

This study aimed to develop a deep-learning framework generate multi-organ masks from CT images in adult and pediatric patients. A dataset consisting of 4082 ground-truth manual segmentation various databases, including 300 cases, were collected. In strategy#1, the provided by public databases split into training (90%) testing (10% each database named subset #1) cohort. The set was used train multiple nnU-Net networks five-fold cross-validation (CV) for 26 separate organs. next step, trained models strategy #1 missing organs entire dataset. generated data then model CV (strategy#2). Models' performance evaluated terms Dice coefficient (DSC) other well-established image metrics. lowest DSC strategy#1 0.804 ± 0.094 adrenal glands while average > 0.90 achieved 17/26 strategy#2 (0.833 0.177) obtained pancreas, whereas 13/19 For all mutual included #2, our outperformed TotalSegmentator both strategies. addition, on #3. Our with significant variability different producing acceptable results making it well-suited implementation clinical setting.

Language: Английский

---

A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy

Frontiers in Oncology, Journal Year: 2023, Volume and Issue: 13

Published: Aug. 4, 2023

Auto-segmentation with artificial intelligence (AI) offers an opportunity to reduce inter- and intra-observer variability in contouring, improve the quality of contours, as well time taken conduct this manual task. In work we benchmark AI auto-segmentation contours produced by five commercial vendors against a common dataset.The organ at risk (OAR) generated solutions (Mirada (Mir), MVision (MV), Radformation (Rad), RayStation (Ray) TheraPanacea (Ther)) were compared manually-drawn expert from 20 breast, head neck, lung prostate patients. Comparisons made using geometric similarity metrics including volumetric surface Dice coefficient (vDSC sDSC), Hausdorff distance (HD) Added Path Length (APL). To assess saved, manually draw correct recorded.There are differences number CT offered each solution study (Mir 99; MV 143; Rad 83; Ray 67; Ther 86), all offering some lymph node levels OARs. Averaged across structures, median vDSCs good for systems favorably existing literature: Mir 0.82; 0.88; 0.86; 0.87; 0.88. All offer substantial savings, ranging between: breast 14-20 mins; neck 74-93 20-26 35-42 mins. The averaged was similar systems: 39.8 43.6 36.6 min; 43.2 45.2 mins.All evaluated high significantly reduced could be used render radiotherapy workflow more efficient standardized.

Language: Английский

---

Adaptive Region-Specific Loss for Improved Medical Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence, Journal Year: 2023, Volume and Issue: 45(11), P. 13408 - 13421

Published: June 26, 2023

Defining the loss function is an important part of neural network design and critically determines success deep learning modeling. A significant shortcoming conventional functions that they weight all regions in input image volume equally, despite fact system known to be heterogeneous (i.e., some can achieve high prediction performance more easily than others). Here, we introduce a region-specific lift implicit assumption homogeneous weighting for better learning. We divide entire into multiple sub-regions, each with individualized constructed optimal local performance. Effectively, this scheme imposes higher weightings on sub-regions are difficult segment, vice versa . Furthermore, regional false positive negative errors computed during training step penalty adjusted accordingly enhance overall accuracy prediction. Using different public in-house medical datasets, demonstrate proposed regionally adaptive paradigm outperforms methods multi-organ segmentations, without any modification architecture or additional data preparation.

Language: Английский

---

LLM-driven multimodal target volume contouring in radiation oncology

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Oct. 24, 2024

Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates utilization of both image and text-based clinical information.Inspired by recent advancement large language models (LLMs) that can facilitate integration textural information images, here we present an LLM-driven multimodal artificial intelligence (AI), namely LLMSeg, utilizes applicable to task 3-dimensional context-aware target delineation oncology.We validate our proposed LLMSeg within context breast cancer radiotherapy using external validation data-insufficient environments, which attributes highly conducive real-world applications.We demonstrate exhibits markedly improved performance compared conventional unimodal AI models, particularly exhibiting robust generalization data-efficiency.

Language: Английский

---

Data-driven risk stratification and precision management of pulmonary nodules detected on chest computed tomography

Nature Medicine, Journal Year: 2024, Volume and Issue: 30(11), P. 3184 - 3195

Published: Sept. 17, 2024

The widespread implementation of low-dose computed tomography (LDCT) in lung cancer screening has led to the increasing detection pulmonary nodules. However, precisely evaluating malignancy risk nodules remains a formidable challenge. Here we propose triage-driven Chinese Lung Nodules Reporting and Data System (C-Lung-RADS) utilizing medical checkup cohort 45,064 cases. system was operated stepwise fashion, initially distinguishing low-, mid-, high- extremely high-risk based on their size density. Subsequently, it progressively integrated imaging information, demographic characteristics follow-up data pinpoint suspicious malignant refine scale. multidimensional achieved state-of-the-art performance with an area under curve (AUC) 0.918 (95% confidence interval (CI) 0.918-0.919) internal testing dataset, outperforming single-dimensional approach (AUC 0.881, 95% CI 0.880-0.882). Moreover, C-Lung-RADS exhibited superior sensitivity compared Lung-RADS v2022 (87.1% versus 63.3%) independent cohort, which screened using mobile scanners broaden accessibility resource-constrained settings. With its foundation precise stratification tailored management, this minimized unnecessary invasive procedures for low-risk cases recommended prompt intervention avert diagnostic delays. This potential enhance decision-making paradigm facilitate more efficient diagnosis during routine checkups as well scenarios.

Language: Английский

---

The clinical application of artificial intelligence in cancer precision treatment

Journal of Translational Medicine, Journal Year: 2025, Volume and Issue: 23(1)

Published: Jan. 27, 2025

Language: Английский

---

A frequency attention-embedded network for polyp segmentation

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 10, 2025

Gastrointestinal polyps are observed and treated under endoscopy, so there presents significant challenges to advance endoscopy imaging segmentation of polyps. Current methodologies often falter in distinguishing complex polyp structures within diverse (mucosal) tissue environments. In this paper, we propose the Frequency Attention-Embedded Network (FAENet), a novel approach leveraging frequency-based attention mechanisms enhance accuracy significantly. FAENet ingeniously segregates processes image data into high low-frequency components, enabling precise delineation boundaries internal by integrating intra-component cross-component mechanisms. This method not only preserves essential edge details but also refines learned representation attentively, ensuring robust across varied conditions. Comprehensive evaluations on two public datasets, Kvasir-SEG CVC-ClinicDB, demonstrate FAENet's superiority over several state-of-the-art models terms Dice coefficient, Intersection Union (IoU), sensitivity, specificity. The results affirm that advanced significantly improve quality, outperforming traditional contemporary techniques. success indicates its potential revolutionize clinical practices, fostering diagnosis efficient treatment gastrointestinal

Language: Английский

---