Klasifikasi Alexnet dan Deteksi Tepi Canny untuk Identifikasi Citra Repomedunm

Jurnal Informasi dan Teknologi, Год журнала: 2023, Номер unknown, С. 191 - 198

Опубликована: Апрель 30, 2023

Deteksi dini kanker serviks dapat mencegah dan menunda kematian, salah satunya dengan memanfaatkan teknologi komputer untuk mendiagnosa berbagai jenis sel serviks. Penelitian dilakukan terhadap citra Pap smear yang diambil dari RepomedUNM tujuan mengklasifikasikan menjadi dua kelas yaitu normal abnormal menggunakan metode AlexNet. Proses awal klasifikasi terdiri mengubah ukuran asli skala abu-abu. ini juga bertujuan mendeteksi tepi pap koilocyt. Canny mendapatkan nilai luas, keliling diameter sitoplasma inti (nukleus). deteksi proses cropping, grayscale, segmentasi thresholding. Hasil 2000 menghasilkan akurasi sebesar 97,66% hasil 50 mampu memberikan baik sebenarnya hasilnya.

---

TransLevelSet: Integrating Vision Transformers with Level-Sets for Medical Image Segmentation

Neurocomputing, Год журнала: 2024, Номер 599, С. 128077 - 128077

Опубликована: Сен. 1, 2024

Язык: Английский

---

Explaining Deep Learning Models Applied in Histopathology: Current Developments and the Path to Sustainability

Studies in health technology and informatics, Год журнала: 2024, Номер unknown

Опубликована: Авг. 22, 2024

The digital pathology landscape is in continuous expansion. digitalization of slides using WSIs (Whole Slide Images) fueled the capacity automatic support for diagnostics. paper presents an overview current state art methods used histopathological practice explaining CNN classification useful experts. Following study we observed that deep learning models are still underused and pathologists do not trust them. Also need to point out order get a sustainable use experts models. In that, they understand how results generated this information correlates with their prior knowledge obtaining can highlighted study.

Язык: Английский

---

XDecompo: Explainable Decomposition Approach in Convolutional Neural Networks for Tumour Image Classification

Sensors, Год журнала: 2022, Номер 22(24), С. 9875 - 9875

Опубликована: Дек. 15, 2022

Of the various tumour types, colorectal cancer and brain tumours are still considered among most serious deadly diseases in world. Therefore, many researchers interested improving accuracy reliability of diagnostic medical machine learning models. In computer-aided diagnosis, self-supervised has been proven to be an effective solution when dealing with datasets insufficient data annotations. However, image often suffer from irregularities, making recognition task even more challenging. The class decomposition approach provided a robust such challenging problem by simplifying boundaries dataset. this paper, we propose model, called XDecompo, improve transferability features pretext downstream task. XDecompo designed based on affinity propagation-based effectively encourage explainable component highlight important pixels that contribute classification explain effect speciality extracted features. We also explore generalisability handling different datasets, as histopathology for images. quantitative results demonstrate robustness high 96.16% 94.30% CRC images, respectively. demonstrated its generalization capability achieved (both quantitatively qualitatively) compared other Moreover, post hoc method used validate feature transferability, demonstrating highly accurate representations.

Язык: Английский

---

TAHIR: Transformer-Based Affine Histological Image Registration

Lecture notes in computer science, Год журнала: 2023, Номер unknown, С. 541 - 552

Опубликована: Янв. 1, 2023

Язык: Английский

---