Mitotic Index Determination on Live Cells From Label-Free Acquired Quantitative Phase Images Using a Supervised Autoencoder

Pognonec, Philippe; Gustovic, Axel; Djabari, Zied; Pourcher, Thierry; Barlaud, Michel

doi:10.1109/tcbb.2021.3115876

“…Thus, two effects are at play during training: the classification loss trains the encoder to be a good classifier between malignant and benign nodules, and the reconstruction loss trains the encoder to learn a good representation of the data to facilitate the task of the decoder (which is also trained during this process). See [44], [45], [46], [47] and Fig. 2 for more details.…”

Section: A New Supervised Autoencoder Architecturementioning

confidence: 99%

Low-cost Thyroid Nodule Diagnosis Using a Supervised Autoencoder Neural network

Barlaud¹

2023

Preprint

0

View full text Add to dashboard Cite

Background: Thyroid Nodules are more and more widespread, with the frequency of thyroid cancers increasing accordingly. In routine practice, the practician's goal is to determine if a nodule is malignant or suspicious, and thus requires surgery. However, nearly one-third of thyroid nodules fall into the 'indeterminate' classification segment, often leading to the use of surgery as a diagnostic tool, when it could have been avoided with a better preoperative diagnosis. Molecular tests exist to address this issue, but they are markedly onerous. Results: In this paper, we present an accurate, cost-less method to predict the malignancy of thyroid nodules using a categorical thyroid nodules dataset. The prediction is achieved through the use of a new supervised autoencoder neural network. Results show that the Supervised Autoencoder Neural Network outperforms classical classification methods on all evaluation metrics. A proof-of-concept Graphical User Interface was developed to demonstrate the medical usefulness of the latent space of the trained network. Conclusions: Aside from the prediction itself, the Supervised Autoencoder Neural Network provides three medically interesting characteristics: a prediction confidence score, consistent feature ranking, and an interpretable latent space. All of those characteristics are valuable from the practician's point of view, as they allow for an efficient, cost-less and well-informed prognosis.

show abstract

“…Thus, two effects are at play during training: the classification loss trains the encoder to be a good classifier between malignant and benign nodules, and the reconstruction loss trains the encoder to learn a good representation of the data to facilitate the task of the decoder (which is also trained during this process). See [44], [45], [46], [47] and Fig. 2 for more details.…”

Section: A New Supervised Autoencoder Architecturementioning

confidence: 99%

Low-cost Thyroid Nodule Diagnosis Using a Supervised Autoencoder Neural network

Barlaud¹

2023

Preprint

0

View full text Add to dashboard Cite

Background: Thyroid Nodules are more and more widespread, with the frequency of thyroid cancers increasing accordingly. In routine practice, the practician's goal is to determine if a nodule is malignant or suspicious, and thus requires surgery. However, nearly one-third of thyroid nodules fall into the 'indeterminate' classification segment, often leading to the use of surgery as a diagnostic tool, when it could have been avoided with a better preoperative diagnosis. Molecular tests exist to address this issue, but they are markedly onerous. Results: In this paper, we present an accurate, cost-less method to predict the malignancy of thyroid nodules using a categorical thyroid nodules dataset. The prediction is achieved through the use of a new supervised autoencoder neural network. Results show that the Supervised Autoencoder Neural Network outperforms classical classification methods on all evaluation metrics. A proof-of-concept Graphical User Interface was developed to demonstrate the medical usefulness of the latent space of the trained network. Conclusions: Aside from the prediction itself, the Supervised Autoencoder Neural Network provides three medically interesting characteristics: a prediction confidence score, consistent feature ranking, and an interpretable latent space. All of those characteristics are valuable from the practician's point of view, as they allow for an efficient, cost-less and well-informed prognosis.

show abstract

Proline-rich acidic protein 1 upregulates mitotic arrest deficient 1 to promote cisplatin-resistance of colorectal carcinoma by restraining mitotic checkpoint complex assembly

Song¹,

Chen²,

Yu³

et al. 2023

J. Cancer

0

View full text Add to dashboard Cite

Background: The mechanism underlying cisplatin resistance in colorectal carcinoma (CRC) has not yet been elucidated. This study is aimed to illustrate the indispensable role of proline-rich acidic protein 1 (PRAP1) in cisplatin-resistant CRC. Methods: Cell viability and apoptosis were monitored using cell counting kit-8 and flow cytometry. Immunofluorescence and morphological analysis were used to determine mitotic arrest in cells. In vivo drug resistance was evaluated using a tumor xenograft assay. Results: PRAP1 was highly expressed in cisplatin-resistant CRC. PRAP1-upregulation in HCT-116 cells increased chemoresistance to cisplatin, whereas RNAi-mediated knockdown of PRAP1 sensitized cisplatin-resistant HCT-116 cells (HCT-116/DDP) to cisplatin. PRAP1-upregulation in HCT-116 cells hindered mitotic arrest and the formation of mitotic checkpoint complexes (MCC), followed by an increase in multidrug-resistant proteins such as p-glycoprotein 1 and multidrug resistance-associated protein 1, while PRAP1-knockdown in HCT-116/DDP cells partly restored colcemid-induced mitotic arrest and MCC assembly, resulting in decreased multidrug-resistant protein levels. PRAP1 downregulation-mediated sensitization to cisplatin in HCT-116/DDP cells was abolished by the inhibition of mitotic kinase activity by limiting MCC assembly. Additionally, PRAP1-upregulation increased cisplatin-resistance in CRC in vivo . Mechanistically, PRAP1 increased the expression of mitotic arrest deficient 1 (MAD1), that competitively binds to mitotic arrest deficient 2 (MAD2) in cisplatin-resistant CRC cells, leading to failed assembly of MCC and subsequent chemotherapy resistance. Conclusion: PRAP1-overexpression caused cisplatin resistance in CRC. Possibly, PRAP1 induced an increase in MAD1, which competitively interacted with MAD2 and subsequently restrained the formation of MCC, resulting in CRC cells escape from the supervision of MCC and chemotherapy resistance.

show abstract

Mitotic Index Determination on Live Cells From Label-Free Acquired Quantitative Phase Images Using a Supervised Autoencoder

Cited by 3 publications

References 32 publications

Low-cost Thyroid Nodule Diagnosis Using a Supervised Autoencoder Neural network

Low-cost Thyroid Nodule Diagnosis Using a Supervised Autoencoder Neural network

Low-cost Thyroid Nodule Diagnosis Using a Supervised Autoencoder Neural network

Proline-rich acidic protein 1 upregulates mitotic arrest deficient 1 to promote cisplatin-resistance of colorectal carcinoma by restraining mitotic checkpoint complex assembly

Contact Info

Product

Resources

About