Prototypical Models for Classifying High-Risk Atypical Breast Lesions

Parvatikar, Akash; Choudhary, Om Prakash; Ramanathan, Arvind; Jenkins, Rebekah; Navolotskaia, Olga; Carter, Gloria; Tosun, Akif Burak; Fine, Jeffrey L.; Chennubhotla, S. Chakra

doi:10.1007/978-3-030-87237-3_14

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Manual analysis of pathological slices is extremely time-consuming and labor-intensive, and some critical diagnostic information may be missed ( 1 ). In addition, the existence of difficult or ambiguous cases in pathology has aggravated the subjectivity and randomness of pathological diagnosis, resulting in inconsistent diagnoses by multiple diagnoses or different experts ( 2 ). The latest reports indicate that the clinical need for pathological analysis is increasing, and while skilled pathologists are in shortage ( 3 ).…”

Section: Introductionmentioning

confidence: 99%

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis

Jiang

Sui

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

IntroductionManual inspection of histopathological images is important in clinical cancer diagnosis. Pathologists implement pathological diagnosis and prognostic evaluation through the microscopic examination of histopathological slices. This entire process is time-consuming, laborious, and challenging for pathologists. The modern use of whole-slide imaging, which scans histopathology slides to digital slices, and analysis using computer-aided diagnosis is an essential problem.MethodsTo solve the problem of difficult labeling of histopathological data, and improve the flexibility of histopathological analysis in clinical applications, we herein propose a semi-supervised learning algorithm coupled with consistency regularization strategy, called“Semi- supervised Histopathology Analysis Network”(Semi-His-Net), for automated normal-versus-tumor and subtype classifications. Specifically, when inputted disturbing versions of the same image, the model should predict similar outputs. Based on this, the model itself can assign artificial labels to unlabeled data for subsequent model training, thereby effectively reducing the labeled data required for training.ResultsOur Semi-His-Net is able to classify patches from breast cancer histopathological images into normal tissue and three other different tumor subtypes, achieving an accuracy was 90%. The average AUC of cross-classification between tumors reached 0.893.DiscussionTo overcome the limitations of visual inspection by pathologists for histopathology images, such as long time and low repeatability, we have developed a deep learning-based framework (Semi-His-Net) for automatic classification subdivision of the subtypes contained in the whole pathological images. This learning-based framework has great potential to improve the efficiency and repeatability of histopathological image diagnosis.

show abstract

Section: Introductionmentioning

confidence: 99%