Viable and necrotic tumor assessment from whole slide images of osteosarcoma using machine-learning and deep-learning models

Arunachalam, Harish Babu; Mishra, Rashika; Daescu, Ovidiu; Cederberg, Kevin B; Rakheja, Dinesh; Sengupta, Anita; Léonard, David; Hallac, Rami R.; Leavey, Patrick J.

doi:10.1371/journal.pone.0210706

Cited by 103 publications

(91 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To overcome the problem caused by small datasets, in the paper, a deep model with Siamese network (DS-Net) was designed to automatically classify osteosarcoma images from TCIA. 32 In recent years, some research literatures [33][34][35][36][37] have proposed some methods for histological classification in osteosarcoma using deep learning methods. It should be noted that the method in Ref.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep model with Siamese network for viable and necrotic tumor regions assessment in osteosarcoma

Fu¹

2020

Medical Physics

View full text Add to dashboard Cite

To achieve automatic classification of viable and necrotic tumor regions in osteosarcoma, most of the existing deep learning methods can only design a simple model to prevent overfitting on small datasets, which leads to the weak ability of extracting image features and low accuracy of the models. In order to solve the above problem, a deep model with Siamese network (DS-Net) was designed in this paper. Methods: The DS-Net constructed on the basis of full convolutional networks is composed of an auxiliary supervision network (ASN) and a classification network. The construction of the ASN based on the Siamese network aims to solve the problem of a small training set (the main bottleneck of deep learning in medical images). It uses paired data as the input and updates the network through combined labels. The classification network uses the features extracted by the ASN to perform accurate classification. Results: Pathological diagnosis is the most accurate method to identify osteosarcoma. However, due to intraclass variation and interclass similarity, it is challenging for pathologists to accurately identify osteosarcoma. Through the experiments on hematoxylin and eosin (H&E)-stained osteosarcoma histology slides, the DS-Net we constructed can achieve an average accuracy of 95.1%. Compared with existing methods, the DS-Net performs best in the test dataset. Conclusions: The DS-Net we constructed can not only effectively realize the histological classification of osteosarcoma, but also be applicable to many other medical image classification tasks affected by small datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

“…[35] is the same as the deep learning method in Ref. [37]. However, due to the limitations of small sample sets, these deep learning-based methods can only design smaller networks, resulting in weaker ability to extract network features and unsatisfactory performance.…”

Section: Introductionmentioning

confidence: 99%

Deep model with Siamese network for viable and necrotic tumor regions assessment in osteosarcoma

Fu¹

2020

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Interestingly, despite not being re ected on its effect on OSA growth, sustained low-dose CDDP treatment was linked to an evident reduction in the proliferating status of OSA cells within the tumor, quite equivalent to combined therapy. Considering that assessment of tumor necrosis in OSA has become a relevant tool for evaluating response to therapy [40,41], adjusted tumor necrotic rates (ATNR) were calculated for all experimental groups (Fig. 5c).…”

Section: Resultsmentioning

confidence: 99%

Drug Repurposing of β-blocker Propranolol in Osteosarcoma: Preclinical Antitumor Efficacy Alone or in Combination with Chemotherapy.

Solernó¹,

Sobol²,

Capobianco³

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Osteosarcoma is still associated with poor response to therapy and alarmingly elevated mortality rates, especially in developing countries, highlighting the urgent need of novel therapeutic strategies. Given that β-adrenergic receptor (β-AR) signaling regulates many cellular processes involved in the initiation and progression of cancer, multiple efforts have been made to repurpose non-selective β-blocker propranolol in oncology. Considering the unsatisfied clinical needs of osteosarcoma, we evaluated the in vitro and in vivo antitumoral activity of propranolol as a monotherapy or in combination with metronomic chemotherapy, in β-AR-expressing human osteosarcoma cells. Methods: In vitro anti-osteosarcoma effects of propranolol were assessed on high-density cell growth, chemotaxis, colony-forming ability and three-dimensional spheroids. Cell cycle phase distribution and apoptosis were evaluated using flow cytometry analysis, and quantification of hypodiploid cell population and TUNEL labelling, respectively. Propranolol addition to chemotherapy was evaluated in vitro and in human osteosarcoma xenografts generated in athymic mice.Results: Propranolol significantly impaired MG-63 and U-2 OS cellular growth in a concentration range of 10-100 µM (IC50 ≈ 45µM) and was capable of blocking in vitro protumoral effects triggered by catecholamines. Cytostatic activity of propranolol was associated to reduced mitosis and G0/G1 cell cycle, but not to apoptosis induction. Moreover, β-blocker drastically reduced colony formation, spheroid progression and migration of osteosarcoma cells. Synergistic effects were observed in vitro after combining propranolol with chemotherapeutic agents methotrexate or cisplatin. In vivo, treatment with propranolol (10 mg/kg i.p.), alone and especially in addition to non-interrupted low-dose cisplatin (2 mg/kg i.p.), markedly abrogated xenograft progression, reducing tumor growth rates by 25 or 70%, respectively. After histological analysis, propranolol and cisplatin combined therapy resulted in low tumor mitotic index and increased tumor necrosis. Conclusions: Considering its robust antitumoral effects, β-AR antagonization using β-blocker propranolol seems to be an achievable and cost-effective therapeutic approach to modulate osteosarcoma aggressiveness, in addition to chemotherapy. Propranolol could be proposed as a co-adjuvant agent for the management of osteosarcoma, especially in low- and middle-income countries where access to treatment resources are limited. Further preclinical and clinical studies of propranolol repurposing in osteosarcoma are warranted.

show abstract

“…Arunachalam et al präsentierten eine Methode, um Tumoren zu kartieren [8]. Diese wurde speziell entwickelt, um Nekrosen in Osteosarkomen zu erkennen.…”

Section: Kartierung Von Tumorenunclassified

“…Die Arbeitsgruppe trainierte insgesamt 13 Machine-Learning-Modelle und entwickelte ein Deep-Learning-Modell zu diesem Zweck [8]. Die Autoren betonen explizit die Übertragbarkeit ihrer "tumor assessment pipeline" für andere Arten von Tumoren [8]. Dies würde die Übertragbarkeit für die Ophthalmopathologie erleichtern.…”

Section: Kartierung Von Tumorenunclassified

Deep Learning in der Pathologie: Anwendungsmöglichkeiten und Herausforderungen in der Ophthalmopathologie

Lang

Glatz

Schoelles

et al. 2020

Klin Monbl Augenheilkd

View full text Add to dashboard Cite

Zusammenfassung Einleitung Deep Learning erfährt in den zurückliegenden Jahren eine immer größer werdende Aufmerksamkeit und wird für zahlreiche Fragestellungen genutzt. Da Bildanalyse eine der Stärken von Deep Learning ist, liegt der Schluss nahe, auch pathologische Fragestellungen hiermit zu bearbeiten. Ziel dieser Arbeit ist es, aus der allgemeinen Pathologie mögliche Deep-Learning-Ansätze zu identifizieren, die in der Ophthalmopathologie genutzt werden könnten. Zudem soll anhand der Daten eines Jahres der Anteil der potenziell interessanten Präparate für Deep Learning sowie der notwendige Aufwand abgeschätzt werden. Methoden Es erfolgte zunächst eine Literaturrecherche nach Deep-Learning-Modellen und deren Einsatzmöglichkeiten im Bereich der Pathologie. Um den potenziellen Nutzen abzuschätzen, wurde in einem 2. Schritt für die identifizierten Modelle die Anzahl an geeigneten Präparaten im Jahr 2019 ermittelt und in Relation zu der resultierenden Datenmenge und der Scan-Zeit gesetzt, um die Machbarkeit abzuschätzen. Ergebnisse Wir identifizierten 7 besonders interessante Themenbereiche: Festlegen von Regions of Interest (ROI), Einordnen von histologischen Bildern in Scoring-Systeme, Kartieren von Tumoranteilen, Differenzierung verschiedener Arten von Entzündung, Erkennen verschiedener kutaner Tumoren, Klassifizierung von Lymphomen und Vorhersage des Outcomes von Patienten anhand der Histologie von Tumoren. Innerhalb eines Jahres wären für die o. g. Modelle insgesamt 831 Fälle (43%) infrage gekommen. Das Erstellen von Whole Slide Images (WSI) für alle Präparate hätte eine Speicherkapazität von 630 GB bei einer Scan-Zeit von 35 h benötigt. Schlussfolgerung Es existieren mehrere Deep-Learning-Ansätze, die auch für die Ophthalmopathologie interessant sind. Die meisten müssten für die ophthalmopathologischen Fragestellungen speziell trainiert werden. Um Deep-Learning-Ansätze verfolgen zu können, ist es notwendig, eine gute Infrastruktur aufzubauen mit der Möglichkeit, WSI zu erstellen und dauerhaft zu speichern, was technisch machbar erscheint. Zukünftige Studien sollten die konkrete praktische Umsetzung bisheriger Deep-Learning-Möglichkeiten für die Ophthalmopathologie zum Thema haben.

show abstract

Viable and necrotic tumor assessment from whole slide images of osteosarcoma using machine-learning and deep-learning models

Cited by 103 publications

References 37 publications

Deep model with Siamese network for viable and necrotic tumor regions assessment in osteosarcoma

Deep model with Siamese network for viable and necrotic tumor regions assessment in osteosarcoma

Drug Repurposing of β-blocker Propranolol in Osteosarcoma: Preclinical Antitumor Efficacy Alone or in Combination with Chemotherapy.

Deep Learning in der Pathologie: Anwendungsmöglichkeiten und Herausforderungen in der Ophthalmopathologie

Contact Info

Product

Resources

About