CNN Based Autoencoder Application in Breast Cancer Image Retrieval

Minarno, Agus Eko; Ghufron, Kharisma Muzaki; Sabrila, Trifebi Shina; Husniah, Lailatul; Sumadi, Fauzi Dwi Setiawan

doi:10.1109/isitia52817.2021.9502205

Cited by 15 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method demonstrated superior performance in matching image pairs, as evidenced by the results presented in Table 2. Specifically, our approach outperformed two previously reported methods, namely 23 and 45 , with precision scores of 92% and 91%, respectively, for both evaluation criteria (EV1 and EV2). These results suggest that our approach is highly effective in accurately identifying patterns in breast cancer images.…”

Section: Discussion and Resultsmentioning

confidence: 56%

“…In recent years, CBMIR has gone through a renaissance with the promise of revolution. In a previous study 23 , a CNN-based AE was applied to the BreaKHis data set with the aim of minimizing misinformation and evaluating the performance of CBMIR in a binary scenario. However, the reconstructed images produced by this method were found to be blurry, indicating that the extracted features by the AE were not robust enough to reconstruct the original image.…”

Section: Content-based Medical Image Retrieval (Cbmir)mentioning

confidence: 99%

See 1 more Smart Citation

Towards More Transparent and Accurate Cancer Diagnosis with an Unsupervised CAE Approach

Tabatabaei¹,

Colomer²,

Moll³

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Digital pathology has significantly impacted the cancer diagnosis field, with Content-Based Medical Image Retrieval (CBMIR) emerging as a powerful tool for analyzing histopathological Whole Slide Images (WSIs). CBMIR allows users to search a database for similar content to a query, providing pathologists with access to collections of cases with comparable features. This can improve the reliability of diagnostic references and help in making more accurate and timely diagnoses. Objective: In 2020, the Global Cancer Observatory (GCO) reported that breast cancer is the most prevalent cancer type in both men and women, accounting for 11.7% of all cases, while prostate cancer is the second most common cancer type in men, comprising 14.1% of cases. The aim of the proposed Unsupervised CBMIR (UCBMIR) is to replicate the traditional cancer diagnosis workflow and provide a dependable method for supporting pathologists when making diagnostic conclusions based on WSIs. By reducing the workload of pathologists, this approach could potentially enhance the accuracy and efficiency of cancer diagnosis. Method and results: The study presents an innovative approach to address the problem of the lack of labeled histopathological images in CBMIR. A customized unsupervised Convolutional Auto Encoder (CAE) was developed to extract 200 features per image, which were then used by the search engine component. The proposed UCBMIR was evaluated using two widely used numerical techniques in CBMIR and visual evaluation, and compared with a classifier to determine if retrieved images belong to the same cancer type as the query. The validation process was conducted using three distinct data sets, with an external evaluation to demonstrate its effectiveness. The UCBMIR outperformed previous studies, achieving a top 5 recall of 99% and 80% on BreaKHis and SICAPv2, respectively, using the first evaluation technique. Using the second evaluation technique, UCBMIR achieved precision rates of 91% and 70% for BreaKHis and SICAPv2, respectively. Moreover, the UCBMIR was able to identify various patterns in patches and achieved an accuracy of 81% in the top 5 when tested on an external image from Arvaniti, having been trained using SICAPv2 with the second evaluation technique.

show abstract

Section: Discussion and Resultsmentioning

confidence: 56%

Section: Content-based Medical Image Retrieval (Cbmir)mentioning

confidence: 99%

Towards More Transparent and Accurate Cancer Diagnosis with an Unsupervised CAE Approach

Tabatabaei¹,

Colomer²,

Moll³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…the application of a binary hash-mapping to reduce the dimensions of the feature vectors; Minarno et al 19 used a CNN-based auto-encoder method in the feature extraction process to improve the results of the retrieval process; Mbilinyi et al 20 used a deep metric learning approach and the triplet loss to learn a model that receives an image and a text description highlighting specific diagnoses the retrieved images should have. In summary, feature representation is performed in one of the following ways: statistical measures, hand-crafted features, learned features, or a combination of the previously mentioned strategies.…”

Section: Introductionmentioning

confidence: 99%

Computer-aided diagnosis through medical image retrieval in radiology

Silva

Gonçalves

Härmä

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Currently, radiologists face an excessive workload, which leads to high levels of fatigue, and consequently, to undesired diagnosis mistakes. Decision support systems can be used to prioritize and help radiologists making quicker decisions. In this sense, medical content-based image retrieval systems can be of extreme utility by providing well-curated similar examples. Nonetheless, most medical content-based image retrieval systems work by finding the most similar image, which is not equivalent to finding the most similar image in terms of disease and its severity. Here, we propose an interpretability-driven and an attention-driven medical image retrieval system. We conducted experiments in a large and publicly available dataset of chest radiographs with structured labels derived from free-text radiology reports (MIMIC-CXR-JPG). We evaluated the methods on two common conditions: pleural effusion and (potential) pneumonia. As ground-truth to perform the evaluation, query/test and catalogue images were classified and ordered by an experienced board-certified radiologist. For a profound and complete evaluation, additional radiologists also provided their rankings, which allowed us to infer inter-rater variability, and yield qualitative performance levels. Based on our ground-truth ranking, we also quantitatively evaluated the proposed approaches by computing the normalized Discounted Cumulative Gain (nDCG). We found that the Interpretability-guided approach outperforms the other state-of-the-art approaches and shows the best agreement with the most experienced radiologist. Furthermore, its performance lies within the observed inter-rater variability.

show abstract

“…In recent years, CBMIR has gone through a renaissance with the promise of revolution. In a previous study [25], a CNN-based AE was applied to the BreaKHis data set with the aim of minimizing misinformation and evaluating the performance of CBMIR in a binary scenario. However, the reconstructed images produced by this method were found to be blurry, indicating that the extracted features by the AE were not robust enough to reconstruct the original image.…”

Section: Content-based Medical Image Retrieval (Cbmir)mentioning

confidence: 99%

Toward More Transparent and Accurate Cancer Diagnosis With an Unsupervised CAE Approach

Tabatabaei,

Colomer,

Moll

et al. 2023

IEEE Access

View full text Add to dashboard Cite

According to the Global Cancer Observatory, 2020, breast cancer is the most prevalent cancer type in both genders (11.7%), while prostate cancer is the second most common cancer type in men (14.1%). In digital pathology, Content-Based Medical Image Retrieval (CBMIR) is a powerful tool for improving cancer diagnosis by searching for similar histopathological Whole Slide Images (WSIs). CBMIR empowers pathologists to explore similar patches to their query, enhancing diagnostic reliability and accuracy. In this paper, a customized unsupervised Convolutional Auto Encoder (CAE) was developed in the proposed Unsupervised CBMIR (UCBMIR) to replicate the traditional cancer diagnosis workflow, offering the potential to enhance diagnostic accuracy and efficiency by reducing pathologists' workload. Furthermore, it provides a more transparent supporting tool for pathologists in cancer diagnosis. UCBMIR was evaluated using two widely used numerical techniques in CBMIR, visual techniques, and compared with a classifier. Validation encompassed three data sets, including an external evaluation to demonstrate its effectiveness. UCBMIR achieved 99% and 80% top 5 recalls on BreaKHis and SICAPv2 with the first evaluation technique while using the second technique, it reached 91% and 70% precision for BreaKHis and SICAPv2, respectively. Moreover, UCBMIR displayed a strong capability to identify diverse patterns, yielding 81% accuracy in the top 5 predictions on an external image from Arvaniti. The proposed unsupervised CBMIR tool delivered 83% accuracy in retrieving images with the same cancer type.

show abstract

CNN Based Autoencoder Application in Breast Cancer Image Retrieval

Cited by 15 publications

References 15 publications

Towards More Transparent and Accurate Cancer Diagnosis with an Unsupervised CAE Approach

Towards More Transparent and Accurate Cancer Diagnosis with an Unsupervised CAE Approach

Computer-aided diagnosis through medical image retrieval in radiology

Toward More Transparent and Accurate Cancer Diagnosis With an Unsupervised CAE Approach

Contact Info

Product

Resources

About